fix(session): retry top-level stream request timeouts

[fashen97]

Issue for this PR

Closes #39221

Type of change

• Bug fix
• New feature
• Refactor / code improvement
• Documentation

What does this PR do?

Some OpenAI Responses-compatible providers return HTTP 200 and then emit this
SSE error event:

{"type":"error","sequence_number":0,"code":"request_timeout","message":"stream error: stream disconnected before completion"}

parseStreamError() only read body.error.code, so the top-level timeout was
not classified as retryable and the turn stopped. This change recognizes the
top-level request_timeout code and uses the existing retry policy.

This complements #39413, which handles an HTTP 408 response status. This PR
handles the separate HTTP 200 plus SSE error response shape.

How did you verify your code works?

• bun test test/session/retry.test.ts (34 pass)
• bun typecheck
• bunx prettier --check packages/opencode/src/provider/error.ts packages/opencode/test/session/retry.test.ts
• The regression test exercises MessageV2.fromError() through
  SessionRetry.retryable() and verifies the parsed error is retryable.

Screenshots / recordings

Not a UI change.

Checklist

• I have tested my changes locally
• I have not included unrelated changes in this PR

[github-actions]

Thanks for your contribution!

This PR doesn't have a linked issue. All PRs must reference an existing issue.

Please:

1. Open an issue describing the bug/feature (if one doesn't exist)
2. Add Fixes #<number> or Closes #<number> to this PR description

See CONTRIBUTING.md for details.

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

Potential Related PRs:

1. fix(session): retry HTTP 408 request timeouts #39413: fix(session): retry HTTP 408 request timeouts

   • fix(session): retry HTTP 408 request timeouts #39413
   • Why related: This PR is explicitly mentioned in your description as complementary. fix(session): retry HTTP 408 request timeouts #39413 handles HTTP 408 responses, while your PR (40268) handles HTTP 200 responses with request_timeout error events in the SSE stream.

2. fix(provider): recover stalled model streams #40010: fix(provider): recover stalled model streams

   • fix(provider): recover stalled model streams #40010
   • Why related: Addresses stream recovery issues similar to the timeout handling your PR implements.

3. fix(opencode): make long-lived provider streams robust to silent SSE terminations #39970: fix(opencode): make long-lived provider streams robust to silent SSE terminations

   • fix(opencode): make long-lived provider streams robust to silent SSE terminations #39970
   • Why related: Handles SSE stream resilience, which overlaps with your timeout error classification work.

These are related PRs addressing similar stream reliability concerns, but #39413 is the most directly relevant since your PR explicitly complements it.

[github-actions]

Thanks for updating your PR! It now meets our contributing guidelines. 👍